INDEX

Explanations

phrases that indicate limitations or lack of knowledge

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 fermés

-0.61

-0.59

 efficaces

-0.51

abestanden

-0.51

########.

-0.50

 اثر

-0.50

นวน

-0.49

sû

-0.49

SVN

-0.49

 récents

-0.48

POSITIVE LOGITS

MigrationBuilder

0.78

 previously

0.64

encodeWith

0.62

 otherwise

0.62

 sonst

0.61

yet

0.61

 heretofore

0.60

 autrement

0.59

 OTHERWISE

0.59

 zuvor

0.58

Activations Density 0.244%

phrases that indicate limitations or lack of knowledge

No Comments

No Known Activations